Soft images segmentation

Abstract

Images obtained by introscopy and radiography have characteristics of much noise. They are soft images and therefore the interpretation of data on the images is complex. For such images the application of prevalent methods of segmentation founded on the analysis of a histogram of image brightness is difficult. In the present paper methods of segmentation of images founded on approximating a Fourier transform and textured signs of the image obtained from the grey level co-occurrence matrix are investigated.